© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9289
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Egypte
    -0.57
     I
    -0.55
     affaire
    -0.53
    <eos>
    -0.51
    CommandText
    -0.43
    lagte
    -0.42
     juicio
    -0.39
     we
    -0.39
    Égypte
    -0.39
    служи
    -0.38
    POSITIVE LOGITS
     saites
    0.97
     Anſ
    0.91
    ſelves
    0.90
    ſelf
    0.87
     Houſe
    0.86
    出版年
    0.86
     itſelf
    0.84
    ########.
    0.83
     raiſ
    0.82
     againſt
    0.81
    Activations Density 0.288%

    No Known Activations